Predicting Online Media Effectiveness Based on Smile Responses Gathered Over the Internet
We present an automated method for classifying “liking” and “desire to view again” based on over 1,500 facial responses to media collected over the Internet. This is a very challenging pattern recognition problem that involves robust detection of smile intensities in uncontrolled settings and classi...
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | en_US |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2013
|
Online Access: | http://hdl.handle.net/1721.1/81192 https://orcid.org/0000-0002-5661-0022 |
_version_ | 1811083093013954560 |
---|---|
author | McDuff, Daniel Jonathan Demirdjian, David Picard, Rosalind W. El Kaliouby, Rana |
author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory McDuff, Daniel Jonathan Demirdjian, David Picard, Rosalind W. El Kaliouby, Rana |
author_sort | McDuff, Daniel Jonathan |
collection | MIT |
description | We present an automated method for classifying “liking” and “desire to view again” based on over 1,500 facial responses to media collected over the Internet. This is a very challenging pattern recognition problem that involves robust detection of smile intensities in uncontrolled settings and classification of naturalistic and spontaneous temporal data with large individual differences. We examine the manifold of responses and analyze the false positives and false negatives that result from classification. The results demonstrate the possibility for an ecologically valid, unobtrusive, evaluation of commercial “liking” and “desire to view again”, strong predictors of marketing success, based only on facial responses. The area under the curve for the best “liking” and “desire to view again” classifiers was 0.8 and 0.78 respectively when using a challenging leave-one-commercial-out testing regime. The technique could be employed in personalizing video ads that are presented to people whilst they view programming over the Internet or in copy testing of ads to unobtrusively quantify effectiveness. |
first_indexed | 2024-09-23T12:21:29Z |
format | Article |
id | mit-1721.1/81192 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T12:21:29Z |
publishDate | 2013 |
publisher | Institute of Electrical and Electronics Engineers (IEEE) |
record_format | dspace |
spelling | mit-1721.1/811922022-10-01T09:01:25Z Predicting Online Media Effectiveness Based on Smile Responses Gathered Over the Internet McDuff, Daniel Jonathan Demirdjian, David Picard, Rosalind W. El Kaliouby, Rana Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Media Laboratory Program in Media Arts and Sciences (Massachusetts Institute of Technology) McDuff, Daniel Jonathan el Kaliouby, Rana Demirdjian, David Picard, Rosalind W. We present an automated method for classifying “liking” and “desire to view again” based on over 1,500 facial responses to media collected over the Internet. This is a very challenging pattern recognition problem that involves robust detection of smile intensities in uncontrolled settings and classification of naturalistic and spontaneous temporal data with large individual differences. We examine the manifold of responses and analyze the false positives and false negatives that result from classification. The results demonstrate the possibility for an ecologically valid, unobtrusive, evaluation of commercial “liking” and “desire to view again”, strong predictors of marketing success, based only on facial responses. The area under the curve for the best “liking” and “desire to view again” classifiers was 0.8 and 0.78 respectively when using a challenging leave-one-commercial-out testing regime. The technique could be employed in personalizing video ads that are presented to people whilst they view programming over the Internet or in copy testing of ads to unobtrusively quantify effectiveness. MIT Media Lab Consortium 2013-09-26T14:41:46Z 2013-09-26T14:41:46Z 2013-04 Article http://purl.org/eprint/type/ConferencePaper 9781467355445 9781467355452 http://hdl.handle.net/1721.1/81192 McDuff, Daniel et al. “Predicting Online Media Effectiveness Based on Smile Responses Gathered over the Internet.” IEEE, 2013. 1–7. https://orcid.org/0000-0002-5661-0022 en_US http//dx.doi.org/10.1109/FG.2013.6553750 Proceedings of the 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG 2013) Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT Web Domain |
spellingShingle | McDuff, Daniel Jonathan Demirdjian, David Picard, Rosalind W. El Kaliouby, Rana Predicting Online Media Effectiveness Based on Smile Responses Gathered Over the Internet |
title | Predicting Online Media Effectiveness Based on Smile Responses Gathered Over the Internet |
title_full | Predicting Online Media Effectiveness Based on Smile Responses Gathered Over the Internet |
title_fullStr | Predicting Online Media Effectiveness Based on Smile Responses Gathered Over the Internet |
title_full_unstemmed | Predicting Online Media Effectiveness Based on Smile Responses Gathered Over the Internet |
title_short | Predicting Online Media Effectiveness Based on Smile Responses Gathered Over the Internet |
title_sort | predicting online media effectiveness based on smile responses gathered over the internet |
url | http://hdl.handle.net/1721.1/81192 https://orcid.org/0000-0002-5661-0022 |
work_keys_str_mv | AT mcduffdanieljonathan predictingonlinemediaeffectivenessbasedonsmileresponsesgatheredovertheinternet AT demirdjiandavid predictingonlinemediaeffectivenessbasedonsmileresponsesgatheredovertheinternet AT picardrosalindw predictingonlinemediaeffectivenessbasedonsmileresponsesgatheredovertheinternet AT elkalioubyrana predictingonlinemediaeffectivenessbasedonsmileresponsesgatheredovertheinternet |